A convolutional neural network for sleep stage scoring from raw single-channel EEG. (April 2018)

• Record Type: Journal Article
• Authors: Sors, Arnaud; Bonnet, Stéphane; Mirek, Sébastien; Vercueil, Laurent; Payen, Jean-François
• Is Part Of: Biomedical signal processing and control. Volume 42(2018)
• Page Start: 107
• Page End: 114
• Publication Date: 2018-04
• Subjects: EEG -- Single-channel -- Sleep staging -- Convolutional neural network -- Classification -- Sleep Heart Health Study; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2017.12.001
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: A sleep scoring system based on a convolutional neural network is proposed. The network is trained end-to-end and learns feature detectors on raw EEG. The system is evaluated on a large dataset, which warrants good generalization. Abstract: We present a novel method for automatic sleep scoring based on single-channel EEG. We introduce the use of a deep convolutional neural network (CNN) on raw EEG samples for supervised learning of 5-class sleep stage prediction. The network has 14 layers, takes as input the 30-s epoch to be classified as well as two preceding epochs and one following epoch for temporal context, and requires no signal preprocessing or feature extraction phase. We train and evaluate our system using data from the Sleep Heart Health Study (SHHS), a large multi-center cohort study including expert-rated polysomnographic records. Performance metrics reach the state of the art, with accuracy of 0.87 and Cohen kappa of 0.81. The use of a large cohort with multiple expert raters guarantees good generalization. Finally, we present a method for visualizing class-wise patterns learned by the network.